English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Existing methods for CWS usually rely on a large number of labeled sentencesto train word segmentation models, which are expensive and time-consuming toannotate. Luckily, the unlabeled data is usually easy to collect and manyhigh-quality Chinese lexicons are off-the-shelf, both of which can provideuseful information for CWS. In this paper, we propose a neural approach forChinese word segmentation which can exploit both lexicon and unlabeled data.Our approach is based on a variant of posterior regularization algorithm, andthe unlabeled data and lexicon are incorporated into model training as indirectsupervision by regularizing the prediction space of CWS models. Extensiveexperiments on multiple benchmark datasets in both in-domain and cross-domainscenarios validate the effectiveness of our approach.

Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization